CN103714347A - Facial recognition method and facial recognition device - Google Patents
Facial recognition method and facial recognition device Download PDFInfo
- Publication number
- CN103714347A CN103714347A CN201310746593.1A CN201310746593A CN103714347A CN 103714347 A CN103714347 A CN 103714347A CN 201310746593 A CN201310746593 A CN 201310746593A CN 103714347 A CN103714347 A CN 103714347A
- Authority
- CN
- China
- Prior art keywords
- face
- recognition
- template
- characteristic
- identified person
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Collating Specific Patterns (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a facial recognition method. The facial recognition method comprises the first step of acquiring a facial image, the second step of acquiring facial illuminance, the third step of pretreating the facial image according to the facial illuminanace, the fourth step of extracting facial features from the pretreated facial image, the fifth step of determining whether facial recognition is passed or not by comparing the extracted facial features with all facial templates, the sixth step of reading appointed identity information of a recognized person when the facial recognition fails to be passed by comparing the extracted facial features with all the facial templates, the seventh step of obtaining an appointed facial template according to the appointed identity information of the recognized person, and the eighth step of determining whether the facial recognition is passed or not by comparing the extracted facial features with the appointed facial template. According to the facial recognition method, the probability of misrecognition and the probability of recognition rejection can be lowered, and therefore the success rate of recognition is increased; meanwhile, human intervention is avoided, so that recognition efficiency is improved.
Description
Technical field
The invention belongs to face recognition technology field, relate to a kind of face identification method and face identification device of high recognition efficiency.
Background technology
Face recognition technology is developed and widespread use rapidly in recent years, this is a kind of face database based on known, utilize computing machine or embedded device to analyze facial image, and then utilize Feature Extraction Technology to extract effective identifying information, be used for a special kind of skill of " identification " identity.Particularly, recognition of face is exactly that people's face to be identified and known person face are compared, and draws the relevant information of similarity degree.As shown in Figure 1, generally, image unit constantly gathers human face image information, then by location, extraction face characteristic, and compare according to the whole face templates in extracted face characteristic and face characteristic storehouse, and determine whether recognition of face is passed through.
Along with the continuous popularization in practical application, the problem that face identification system exists also highlights gradually.Such as, face characteristic has changeability, as various condiment, and the variation of human face expression etc., and these variations all may cause face identification system to refuse to know, know by mistake phenomenon in actual applications.Although embedded human face recognition system is conventionally when typing face template, the multi-faceted features of information acquisition people face such as far away by pointing out, near, new line, rotary head, be conducive to improve recognition success rate, but this is still not enough to reduce because face characteristic changes refusing of causing and knows and mistake probability.
Further, recognition of face success ratio is not only subject to face characteristic variability effects, also can be subject to the impact of environment for use condition.Such as, when being applied in outdoor environmental conditions, because sunshine spectral range is very wide, optical filter filter is not fallen, and people just there will be Gao Guang, dash area on the face, or excessively bright, or cross secretly, with off-the-air picture, compare and have bigger difference, this also can make recognition of face rate significantly decline.In addition, also have ambient lights such as daytime, evening to change and also can affect recognition of face rate.Current adaptive algorithm, although solved to a certain extent light and the accrete problem of people's face, misclassification rate is generally higher.And, when scene, environment change, when appearance cannot be verified, need the artificial new template of typing, be able to the object of normal identification.Though can temporarily pass through like this, scene environment and face characteristic variability are large, and in addition, when personnel are more, typing new template again, wastes time and energy, and can not tackle the problem at its root.
Summary of the invention
The present invention, in view of above problem, provides a kind of face identification method, and it can reduce mistake identification, improves recognition success rate, has avoided human intervention simultaneously, has improved recognition efficiency.
One aspect of the present invention provides a kind of face identification method, and it comprises: the step of obtaining facial image; Obtain the step of human face light degree; According to illuminance, facial image is carried out to pretreated step; From pretreated facial image, extract the step of face characteristic; Thereby the face characteristic of extraction and whole face templates are compared to the step of determining whether recognition of face is passed through, and when the face characteristic of extraction is compared not by recognition of face with whole face templates, read the step of the identity information of identified person's appointment; According to the identity information of identified person's appointment, obtain the step of the face template of appointment; The face template of the face characteristic of extraction and appointment is compared, and determine the step whether recognition of face is passed through.
The present invention provides a kind of face identification device on the other hand, and it comprises: identity information reading unit (6), and it directly reads identified person's identity information, image acquisition unit (1), it is for gathering facial image, illumination detecting unit (2), it is for detection of the illuminance of people's face, processing unit (3), it carries out illumination pretreatment according to detected illuminance to gathered facial image, and extracts face characteristic after described illumination pretreatment, storage unit (4), it is for storing many people's identity information, and the face template corresponding with identity information, and the illuminance information corresponding with face template, and recognition unit (5), it is according to the face characteristic being extracted by described processing unit (3), compare with the face template being stored in described storage unit (4), and carry out recognition of face, described recognition unit (5) is at the face characteristic that will be extracted by described processing unit (3), contrast with whole face templates, when recognition of face is not passed through, the identity information of the identified person's who directly reads according to described identity information reading unit (6) appointment, from storage unit (4), obtain the face template of appointment, and the face characteristic that will be extracted by described processing unit (3), compare with the face template of this appointment, judge whether recognition of face is passed through.
Face identification method provided by the invention and face identification device, after extracting face characteristic, this face characteristic and whole face templates are compared, if passed through, recognition of face finishes, if not by; according to identified person's identity information, obtain identified person's appointment face template, and the face template of extracted face characteristic and appointment compared, thereby determine whether recognition of face is passed through.Owing to having carried out supplementary recognition of face, thereby can reduce and identify by mistake and refuse identification, improve recognition success rate, avoid human intervention simultaneously, improve recognition efficiency.
Accompanying drawing explanation
Fig. 1 is the identifying schematic diagram of prior art face identification method;
Fig. 2 is the face identification method face template registering flow path figure that an embodiment of the present invention provides;
Fig. 3 is the recognition of face process flow diagram of the face identification method that provides of an embodiment of the present invention;
Fig. 4 is the detailed step figure of the face identification method of Fig. 3 shown device;
Fig. 5 is that the face template of the face identification method that provides of an embodiment of the present invention upgrades process flow diagram;
Fig. 6 is the theory diagram of the face identification device that provides of an embodiment of the present invention.
Embodiment
For making those skilled in the art understand better technical scheme of the present invention, below in conjunction with the drawings and specific embodiments, face identification method provided by the invention and face identification device are described in detail.In these accompanying drawings, for identical or suitable inscape, mark same numeral.Below be only the preferred forms of face identification method of the present invention and face identification device, the present invention is not limited in following structure and flow process.
Face identification method of the present invention is in order to improve the changeability of adaptive capacity to environment and reply face characteristic, not only when carrying out recognition of face, consider illumination condition, and the face template in meeting while imposing a condition new database more, thereby be convenient to the face characteristic that identification changes.Face identification method of the present invention all can be considered illuminance when identifying neutralization judges whether to upgrade face template, therefore when face template Database, also can gather illuminance information.The process of establishing of present embodiment face identification method face template database is described below in conjunction with Fig. 2.
Fig. 2 is the face identification method face template registering flow path figure that an embodiment of the present invention provides.As shown in Figure 2, first, in step S20, set up personal information database.Set up in advance particularly personal information database, comprise the information such as job number, name, face template, recognition method, authority, reserved byte is for expansion.Then, collector's information in step S21.Mainly comprise user basic information registration, such as job number (ID) and name, ID is unique, must input, otherwise can not carry out next step.After completing steps S21, proceed to step S22 and S23.In step S22, gather people's face information of current personnel.Particularly, user is according to prompting, watches camera attentively, come back, bow, turn left head, right-hand rotation head, gathers the multi-angle frame of people's face as far as possible, and after having gathered facial image, extraction face characteristic Ex, deposits buffer memory in.In order to collect abundant face characteristic, each user at least gathers 3 groups of face templates, and preferably everyone face user gathers 9 to 18 groups of face characteristics as template.In step S23, gather illumination information.That is, the ambient light information while gathering execution step S22, and process according to this light information.After completing steps S22 and S23, proceed to step S24.In step S24, preservation information is entered database.Particularly, when buffer memory face characteristic number reaches m, face characteristic is Ex1, Ex2, Ex3 ... Exm, by this user basic information, skin detection and illuminance are preserved into database, and wherein m is user's face template quantity, for being greater than 1 positive integer.
Face identification method of the present invention mainly comprises: Global Face identification, appointment recognition of face, the identification of secondary Global Face, the checking of people's face, face template upgrade.The face identification method of present embodiment is described below in conjunction with Fig. 3 and Fig. 4.
Fig. 3 is the recognition of face process flow diagram of the face identification method providing of an embodiment of the present invention.
As shown in Figure 3, the face identification method of present embodiment, comprises step S30, carries out Global Face identification,, extracts identified person's face characteristic that is, and this face characteristic and whole face templates are compared, and judges whether recognition of face is passed through.If passed through, recognition of face finishes, and waits for identification next time, if do not passed through, enters step S31, specifies recognition of face.In step S31, by the face template of identified person's face characteristic and appointment, the identified person's who namely stores in database face template is compared, and judges whether by recognition of face.If do not passed through, recognition of face finishes, and waits for identification next time; If passed through, enter step S32.In step S32, carry out the identification of secondary Global Face, in this Global Face identification, reduce the condition that recognition of face is passed through, and face characteristic and whole face templates are compared, judge whether recognition of face is passed through.If do not passed through, recognition of face finishes, and waits for identification next time, if passed through, and the face template similar to identified person in database of record, and enter step S33, carry out the checking of people's face.In step S33, judge that whether the face template of appointment in face template similar to identification people in step S32 and step S31 is same, if not, recognition of face finishes, and waits for identification next time; If so, enter step S34.In step S34, judge whether more new template, if upgraded, enter step S35, upgrade face template, if do not upgraded, recognition of face finishes, and waits for identification next time.In step S35, new template more, after having upgraded, recognition of face finishes, and waits for identification next time.
Face identification method of the present invention, after extracting face characteristic, compares this face characteristic and whole face templates, if passed through, recognition of face finishes, if not by; supplement identification.First the face template of extracted face characteristic and appointment is compared, if similar, again compare with whole face templates, and the condition of passing through is identified in reduction, if passed through, whether the face template of this face template similar with identified person's face characteristic of judgement and appointment is consistent, if consistent, judges that this face characteristic can be by identification.Face identification method of the present invention, owing to carrying out Global Face identification and supplementary recognition of face, therefore can conform and change or face characteristic variation, thereby can reduce, identify by mistake and refuse identification, improve recognition success rate, avoided human intervention simultaneously, improved recognition efficiency.
Further, face identification method of the present invention, after by supplementary recognition of face, also can judge whether to upgrade face template, and when satisfying condition, upgrade face template, thereby can adapt to the variation of face characteristic and the variation of environmental baseline, strengthen the adaptability of the face identification system of this face identification method and employing the method.
Being more than the principle of inventor's face recognition method and main flow process describes, and describes the detailed process of inventor's face recognition method below in conjunction with Fig. 4.
Fig. 4 is the detailed step figure of the face identification method of Fig. 3 shown device.As shown in Figure 4, after starting face identification device 100, first perform step S40.In step S40, gather facial image and light information, particularly, constantly gather people's face information, obtain effective facial image, gather light information simultaneously, obtain now illuminance size Lt.After completing steps S40, proceed to step S41.In step S41, carry out illumination pretreatment, and extract face characteristic Fx.That is, according to the facial image getting, add illumination, deluster and shine or histogram equalization processing, afterwards face normalization is become to unified size, then according to LBP local binary patterns extraction face characteristic Fx.After completing steps S41, proceed to step S42.In step S42, according to the face characteristic extracting, carry out recognition of face.Particularly, the feature of N personnel in Fx and face characteristic storehouse is compared, aspect ratio to time, prepare a plurality of feature identifying schemes, to each scheme with Euclidean distance get comparison apart from the feature of score minimum as candidate's template, record score, ID, face template information; The candidate's template simultaneously each feature identifying schemes identification being obtained is carried out mutual verification, thereby by judging whether candidate's template is that same people judges whether identification is passed through.Then in step S43, obtain face recognition result.If passed through, this end of identification; If do not passed through, proceed to step S44.In step S44, obtain identified person's identity information.Particularly, by identity information reading unit 6, read identified person's identity information, such as job number.After completing steps S44, proceed to step S45.In step S45, according to identification people identity information, specify recognition of face.Particularly, according to identified person, from storage unit 4, obtain this personal information, particularly face characteristic Ex (Ex1, Ex2, Ex3 ... Exm), by Fx and Ex (Ex1, Ex2, Ex3, Exm) carry out aspect ratio pair, such as utilizing Euclidean distance to compare, get apart from score minimum value, when being less than, minimum value specifies recognition of face (or crying job number recognition of face) threshold value Ty, recognition of face is passed through, otherwise refusal.The quantity of the skin detection of preserving when wherein m is for registration.Then in step S46, obtain face recognition result.If, by specifying recognition of face, Resurvey facial image is not identified next time; If passed through, proceed to step S47.In step S47, reduce the threshold value that recognition of face is passed through, supplement recognition of face.Particularly, whether recognition unit 5 is compared the feature of N personnel in Fx and face characteristic storehouse, and pass through according to new threshold decision recognition of face.Then in step S48, obtain face recognition result.If, by specifying recognition of face, Resurvey facial image is not identified next time; If passed through, proceed to step S49.In step S49, judge whether to upgrade face template, if do not upgraded, Resurvey facial image is identified next time.If upgraded, enter step S50, in step S50, upgrade face template.
Fig. 5 is that the face template of the face identification method that provides of an embodiment of the present invention upgrades process flow diagram.The more new technological process of face template is described below in conjunction with Fig. 5.
As shown in Figure 5, the renewal of face template comprises: step S51, obtains by others' information.Particularly, from storage unit 4, obtain this personal information, such as ID, name, illuminance Lt1 and template Ex (Ex1, Ex2, Ex3 ... Exm).Step S52, illuminance judgement.Particularly, Lt and Lt1 are compared, as abs (Lt-Lt1)==0; Or be greater than illuminance and change minimum threshold LTmin, and when being less than illuminance and changing max-thresholds LTmax, represent that the face characteristic Fx obtaining under this illuminance can, as these personnel's alternate template, therefore enter face template renewal.Otherwise, enter step S53, carry out face characteristic judgement.In step S53, by the successful face characteristic Fx of identification and the face characteristic Ex (Ex1 taking out from database, Ex2, Ex3 ... Exm) utilize Euclidean distance to compare, get comparison apart from minimum value, when being greater than face characteristic, this numerical value changes minimum threshold FTmin, and while being less than face characteristic variation max-thresholds FTmax, represent that Fx can, as these personnel's alternate template, therefore enter face template and upgrade.Otherwise, finish this process.
In present embodiment, in order to improve hommization, also before renewal, point out inquiry.Whether particularly, in step S54, to identified person's prompting, upgrade, user can select according to actual conditions.If so, enter step S55, carry out face template renewal, will retain particularly front M-1 the feature of these personnel, with Fx, replace last in feature templates, buffer memory is also upgraded in save data storehouse.If not, finish.
Face identification method provided by the invention is all considered illumination factor in extracting feature and identifying, and process, be beneficial to identification, particularly, when Global Face recognition failures, specify recognition of face, input job number, carry out identification, identification by after reduce again threshold value Global Face identify, so both reduced mistake and known, improved again percent of pass; And can change automatic replacement template (remarks: the template of preserving during registration, is stored in database) according to external environment, face characteristic, thus make to intervene without supernumerary, reach the object of raising the efficiency, improve system flexibility.
The present invention also provides a kind of face identification device on the other hand, and it comprises housing, is provided with image acquisition unit 1, light illuminating unit and display unit on housing.Image acquisition unit 1 is for obtaining facial image, and light illuminating unit comprises a plurality of image acquisition unit 1 light sources around that are arranged on, for the light that irradiates recognition of face region is provided.Display unit is for showing obtained facial image, man-machine interaction prompting, and other information.
Inside at face identification device housing arranges circuit unit, realizes function and the control of recognition of face.The principle of the face identification device of present embodiment is described below in conjunction with Fig. 6.
Fig. 6 is the theory diagram of the face identification device that provides of an embodiment of the present invention.As shown in Figure 6, the face identification device 100 of present embodiment comprises image acquisition unit 1, illumination detecting unit 2, processing unit 3, storage unit 4, recognition unit 5 and identity information acquiring unit 6.
Image acquisition unit 1 is for the image in continuous acquisition recognition of face region, and gathered facial image is sent to processing unit 3.
Storage unit 4 is for storing many people's identity information, and the face template corresponding with identity information, and the illuminance information corresponding with face template.
Recognition unit (5), according to the face characteristic being extracted by processing unit 3, compares with the face template being stored in storage unit 4, and carries out recognition of face.
Further, recognition unit 5 is by the face characteristic being extracted by processing unit 3, compare with the face template of appointment, and during by recognition of face, reduce recognition of face passing threshold, and again by the face characteristic being extracted by processing unit 3, contrast with whole face templates, and determine whether recognition of face is passed through.
Further, recognition unit 5 is reducing recognition of face passing threshold, and while obtaining recognition of face by result, judges whether to upgrade identified person's face template according to the face characteristic by identification and/or the illuminance that detects.
Particularly, recognition unit 5 upgrades identified person's face template when the variation of illuminance corresponding to the relative identified person's face template of detected illuminance is in setting range.Or recognition unit 5 upgrades identified person's face template when the variation of face template of the relative identified person of face characteristic by identification is in setting range.
The face identification device of present embodiment is after extracting face characteristic, this face characteristic and whole face templates are compared, if passed through, recognition of face finishes, if not by; according to identified person's identity information, obtain identified person's appointment face template, and the face template of extracted face characteristic and appointment is compared, thereby further determine whether recognition of face is passed through.Due to according to the appointment recognition of face of identity information, can reduce mistake identification like this, improve recognition success rate, avoid human intervention simultaneously, improve recognition efficiency.
Above embodiment is only used to principle of the present invention is described and the illustrative embodiments that adopts, yet the present invention is not limited thereto.For those skilled in the art, without departing from the spirit and substance in the present invention, can make various modification and improvement.These modification and improvement are also considered as guard interval of the present invention.
Claims (10)
1. a face identification method, is characterized in that, comprising:
By specifying recognition of face, again carry out Global Face identification, and judgement
Obtain the step of facial image;
Obtain the step of human face light degree;
According to illuminance, facial image is carried out to pretreated step;
From pretreated facial image, extract the step of face characteristic;
The face characteristic of extraction and whole face templates are compared and determine the step whether recognition of face is passed through, and
When the face characteristic of extraction is compared not by recognition of face with whole face templates, read the step of the identity information of identified person's appointment;
According to the identity information of identified person's appointment, obtain the step of the face template of appointment;
The face template of the face characteristic of extraction and appointment is compared, and determine the step whether recognition of face is passed through.
2. face identification method as claimed in claim 1, is characterized in that, is comparing, and by after recognition of face, also comprise according to the face characteristic extracting and the face template of appointment:
Reduce the step of recognition of face passing threshold;
Again, by the face characteristic by extracted, contrast with whole face templates, and determine the step whether recognition of face is passed through.
3. face identification method as claimed in claim 2, is characterized in that, is reducing recognition of face passing threshold, and by after recognition of face, is also comprising:
According to the face characteristic by identification and/or the illuminance that detects, judge whether to upgrade the step of identified person's face template.
4. face identification method as claimed in claim 3, is characterized in that, identified person's face template is upgraded in the variation of the illuminance that the relative identified person's face template of illuminance that detects is corresponding in setting range time.
5. face identification method as claimed in claim 4, is characterized in that, identified person's face template is upgraded in the variation of face template of the relative identified person of face characteristic by identification in setting range time.
6. a face identification device, is characterized in that, comprising:
Identity information reading unit (6), it directly reads identified person's identity information;
Image acquisition unit (1), it is for gathering facial image;
Illumination detecting unit (2), it is for detection of the illuminance of people's face;
Processing unit (3), it carries out illumination pretreatment according to detected illuminance to gathered facial image, and extracts face characteristic after described illumination pretreatment;
Storage unit (4), it is for storing many people's identity information, and the face template corresponding with identity information, and the illuminance information corresponding with face template; With
Recognition unit (5), it compares with the face template being stored in described storage unit (4), and carries out recognition of face according to the face characteristic being extracted by described processing unit (3),
Described recognition unit (5) is at the face characteristic that will be extracted by described processing unit (3), contrast with whole face templates, when recognition of face is not passed through, the identity information of the identified person's who directly reads according to described identity information reading unit (6) appointment, from storage unit (4), obtain the face template of appointment, and the face characteristic that will be extracted by described processing unit (3), compare with the face template of this appointment, judge whether recognition of face is passed through.
7. face identification device as claimed in claim 6, it is characterized in that, described recognition unit (5) is at the face characteristic that will be extracted by described processing unit (3), compare with the face template of appointment, and during by recognition of face, reduce recognition of face passing threshold, and the face characteristic that again will be extracted by described processing unit (3), contrast with whole face templates, and determine whether recognition of face is passed through.
8. face identification device as claimed in claim 7, it is characterized in that, described recognition unit (5) is reducing recognition of face passing threshold, and obtain recognition of face when the result, according to the face characteristic by identification and/or the illuminance that detects, judge whether to upgrade identified person's face template.
9. face identification device as claimed in claim 8, is characterized in that, described recognition unit (5) upgrades identified person's face template when the variation of illuminance corresponding to the relative identified person's face template of detected illuminance is in setting range.
10. face identification device as claimed in claim 8, is characterized in that, described recognition unit (5) upgrades identified person's face template when the variation of face template of the relative identified person of face characteristic by identification is in setting range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310746593.1A CN103714347B (en) | 2013-12-30 | 2013-12-30 | Face identification method and face identification device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310746593.1A CN103714347B (en) | 2013-12-30 | 2013-12-30 | Face identification method and face identification device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103714347A true CN103714347A (en) | 2014-04-09 |
| CN103714347B CN103714347B (en) | 2017-08-25 |
Family
ID=50407304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310746593.1A Active CN103714347B (en) | 2013-12-30 | 2013-12-30 | Face identification method and face identification device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103714347B (en) |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156702A (en) * | 2015-04-01 | 2016-11-23 | 北京市商汤科技开发有限公司 | Identity identifying method and equipment |
| CN106326816A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技（杭州）有限公司 | Face recognition system and face recognition method |
| CN106489153A (en) * | 2016-10-13 | 2017-03-08 | 厦门中控生物识别信息技术有限公司 | A kind of face register method and face registering apparatus |
| CN107229892A (en) * | 2016-03-24 | 2017-10-03 | 阿里巴巴集团控股有限公司 | A kind of identification method of adjustment and equipment based on face recognition products |
| CN107657222A (en) * | 2017-09-12 | 2018-02-02 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
| CN107679570A (en) * | 2017-09-27 | 2018-02-09 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN107784724A (en) * | 2017-10-26 | 2018-03-09 | 广州云从信息科技有限公司 | A kind of method for managing security based on recognition of face |
| CN108027883A (en) * | 2015-06-30 | 2018-05-11 | 美国日本电气公司 | Facial-recognition security systems |
| CN108171207A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Face identification method and device based on video sequence |
| CN108376434A (en) * | 2018-02-22 | 2018-08-07 | 陈崇 | A kind of intelligent home control system based on Internet of Things |
| CN108921055A (en) * | 2018-06-15 | 2018-11-30 | 北京蜂盒科技有限公司 | Personal identification method, device, storage medium and electronic equipment |
| CN109522827A (en) * | 2018-10-31 | 2019-03-26 | 维沃移动通信有限公司 | A kind of method, apparatus and terminal device acquiring biological characteristic |
| CN109741475A (en) * | 2018-12-26 | 2019-05-10 | 鲁班长（深圳）科技有限公司 | System of real name Work attendance method, device, system and computer storage medium |
| CN110363150A (en) * | 2019-07-16 | 2019-10-22 | 深圳市商汤科技有限公司 | Data-updating method and device, electronic equipment and storage medium |
| CN110503059A (en) * | 2019-08-27 | 2019-11-26 | 国网电子商务有限公司 | A kind of face identification method and system |
| WO2020164264A1 (en) * | 2019-02-13 | 2020-08-20 | 平安科技（深圳）有限公司 | Facial image recognition method and apparatus, and computer device |
| CN111859000A (en) * | 2020-06-24 | 2020-10-30 | 天津大学 | Method for constructing and updating human face feature database under deep learning model |
| CN112215183A (en) * | 2020-10-21 | 2021-01-12 | 中国银行股份有限公司 | Bank customer identification method and device |
| CN112633250A (en) * | 2021-01-05 | 2021-04-09 | 北京经纬信息技术有限公司 | Face recognition detection experimental method and device |
| CN113487879A (en) * | 2021-07-14 | 2021-10-08 | 湖南省交通科学研究院有限公司 | Integrative cabinet is synthesized to intelligence |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101030244B (en) * | 2006-03-03 | 2010-08-18 | 中国科学院自动化研究所 | Automatic identity discriminating method based on human-body physiological image sequencing estimating characteristic |
| CN101773394B (en) * | 2010-01-06 | 2011-09-07 | 中国航天员科研训练中心 | Identification method and identification system using identification method |
| CN102201061B (en) * | 2011-06-24 | 2012-10-31 | 常州锐驰电子科技有限公司 | Intelligent safety monitoring system and method based on multilevel filtering face recognition |
| CN103440686A (en) * | 2013-07-29 | 2013-12-11 | 上海交通大学 | Mobile authentication system and method based on voiceprint recognition, face recognition and location service |
-
2013
- 2013-12-30 CN CN201310746593.1A patent/CN103714347B/en active Active
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106156702A (en) * | 2015-04-01 | 2016-11-23 | 北京市商汤科技开发有限公司 | Identity identifying method and equipment |
| US11501566B2 (en) | 2015-06-30 | 2022-11-15 | Nec Corporation Of America | Facial recognition system |
| CN106326816A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技（杭州）有限公司 | Face recognition system and face recognition method |
| CN108027883A (en) * | 2015-06-30 | 2018-05-11 | 美国日本电气公司 | Facial-recognition security systems |
| CN107229892A (en) * | 2016-03-24 | 2017-10-03 | 阿里巴巴集团控股有限公司 | A kind of identification method of adjustment and equipment based on face recognition products |
| CN106489153A (en) * | 2016-10-13 | 2017-03-08 | 厦门中控生物识别信息技术有限公司 | A kind of face register method and face registering apparatus |
| CN107657222A (en) * | 2017-09-12 | 2018-02-02 | 广东欧珀移动通信有限公司 | Face identification method and Related product |
| CN107679570A (en) * | 2017-09-27 | 2018-02-09 | 广东欧珀移动通信有限公司 | Solve lock control method and Related product |
| CN107784724A (en) * | 2017-10-26 | 2018-03-09 | 广州云从信息科技有限公司 | A kind of method for managing security based on recognition of face |
| CN108171207A (en) * | 2018-01-17 | 2018-06-15 | 百度在线网络技术（北京）有限公司 | Face identification method and device based on video sequence |
| CN108376434A (en) * | 2018-02-22 | 2018-08-07 | 陈崇 | A kind of intelligent home control system based on Internet of Things |
| CN108921055A (en) * | 2018-06-15 | 2018-11-30 | 北京蜂盒科技有限公司 | Personal identification method, device, storage medium and electronic equipment |
| CN109522827A (en) * | 2018-10-31 | 2019-03-26 | 维沃移动通信有限公司 | A kind of method, apparatus and terminal device acquiring biological characteristic |
| CN109741475A (en) * | 2018-12-26 | 2019-05-10 | 鲁班长（深圳）科技有限公司 | System of real name Work attendance method, device, system and computer storage medium |
| WO2020164264A1 (en) * | 2019-02-13 | 2020-08-20 | 平安科技（深圳）有限公司 | Facial image recognition method and apparatus, and computer device |
| CN110363150A (en) * | 2019-07-16 | 2019-10-22 | 深圳市商汤科技有限公司 | Data-updating method and device, electronic equipment and storage medium |
| CN110503059A (en) * | 2019-08-27 | 2019-11-26 | 国网电子商务有限公司 | A kind of face identification method and system |
| CN111859000A (en) * | 2020-06-24 | 2020-10-30 | 天津大学 | Method for constructing and updating human face feature database under deep learning model |
| CN112215183A (en) * | 2020-10-21 | 2021-01-12 | 中国银行股份有限公司 | Bank customer identification method and device |
| CN112633250A (en) * | 2021-01-05 | 2021-04-09 | 北京经纬信息技术有限公司 | Face recognition detection experimental method and device |
| CN113487879A (en) * | 2021-07-14 | 2021-10-08 | 湖南省交通科学研究院有限公司 | Integrative cabinet is synthesized to intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103714347B (en) | 2017-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103714347A (en) | Facial recognition method and facial recognition device | |
| CN104537336B (en) | A kind of face identification method and system for possessing self-learning function | |
| US9323979B2 (en) | Face recognition performance using additional image features | |
| CN109145742B (en) | Pedestrian identification method and system | |
| CN105447443A (en) | Method and device for improving identification accuracy of iris identification device | |
| CN204155293U (en) | A kind of demo plant based on recognition of face and verification system | |
| CN106778457A (en) | The fingerprint identification method and system of fingerprint recognition rate can be improved | |
| CN109426785B (en) | Human body target identity recognition method and device | |
| CN105447371A (en) | Biological identity identification and verification terminal and electronic system | |
| CN103778409A (en) | Human face identification method based on human face characteristic data mining and device | |
| CN103678984A (en) | Method for achieving user authentication by utilizing camera | |
| CN108604040B (en) | Capturing images for use in facial recognition through efficient use of exposure management | |
| CN103902962A (en) | Shielding or light source self-adaption human face recognition method and device | |
| CN104484652A (en) | Method for fingerprint recognition | |
| CN102982321A (en) | Acquisition method and device for face database | |
| CN103336950A (en) | Human face identification method and system | |
| CN110097510A (en) | A kind of pure color flower recognition methods, device and storage medium | |
| CN108446687A (en) | A kind of adaptive face vision authentication method based on mobile terminal and backstage interconnection | |
| CN110781778B (en) | Access control method and device, storage medium and home system | |
| CN202815870U (en) | Certificate photograph and face automatic identification system | |
| CN109166196A (en) | A kind of hotel's disengaging personnel management methods based on single sample recognition of face | |
| CN202121706U (en) | Intelligent personnel monitoring system | |
| CN111079757A (en) | Clothing attribute identification method and device and electronic equipment | |
| CN117173754A (en) | Non-contact gesture vein recognition method and recognition terminal | |
| CN105809154A (en) | Face identification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |